Unified Analytics Engine for Satellite Data Downlink Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current satellite communication networks face challenges in managing satellite constellations for efficient data downlinking, as existing scheduling systems are manual, unaware of client goals, and unable to perform rapid re-scheduling, leading to inefficiencies and labor-intensive processes.

Innovation Solution

A unified analytics engine and machine learning architecture are integrated into a scheduling system to extract time series features, perform predictive analytics, and optimize satellite constellation access programs, enabling automated and proactive monitoring and scheduling adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual scheduling systems are used for satellite ground station access, then operational control is maintained, but scheduling efficiency and productivity are reduced

Engineering Contradiction:

Improvescheduling efficiencyVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The scheduling system performs self-service by automatically generating satellite access schedules using machine learning models that analyze historical data and predict optimal timing. The system autonomously adjusts schedules based on detected changepoints and performance metrics without requiring manual intervention, thereby improving productivity while managing complexity through automation.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical scheduling operations with automated computational systems. Machine learning models and algorithms substitute human operators in analyzing satellite pass data, detecting changepoints, and generating schedules, transforming a labor-intensive process into an efficient automated system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If data retrieval is performed only during scheduled satellite passes, then communication range constraints are respected, but detection precision and response time are reduced

Engineering Contradiction:

Improveissue detection precisionVSAvoidtime delay

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously monitoring satellite pass data and detecting changepoints that indicate potential issues before they manifest as failures. By analyzing performance metrics in real-time during satellite passes, the system identifies problems early, enabling proactive responses that improve detection precision and reduce time delays in issue identification.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If custom schedulers are used for each satellite operator, then individual client needs are addressed, but system adaptability and coordination are reduced

Engineering Contradiction:

Improvescheduling flexibilityVSAvoidscheduler complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal scheduling system that serves multiple satellite operators and clients through a single coordinated platform. The machine learning-based scheduler handles diverse client requirements and satellite constellations using unified algorithms, providing adaptability to different needs while reducing overall system complexity by eliminating redundant custom schedulers.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Productivity

If satellite passes are monitored without real-time analysis, then computational resources are conserved, but productivity and response capability are reduced

Engineering Contradiction:

Improveoperational efficiencyVSAvoidcomputing resource consumption

Core Design Contradiction:

ProductivityVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by performing real-time analysis only on critical performance metrics and detected changepoints during satellite passes. Rather than analyzing all data continuously, the machine learning models focus computational resources on identifying significant patterns and anomalies, improving operational efficiency while managing computing resource consumption through selective analysis.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12184394B2Unified analytics engine

Publication Date: 2024.12.31 ATLAS SPACE OPERATIONS LLC

AI summary

The present application relates to techniques for proactively monitoring and detecting failures associated with downlinking data during satellite passes. In some embodiments, first data representing a performance of a hardware device during a satellite pass may be obtained and performance metrics may be computed based on the first data. Second data may be generated based on the performance metrics and a first machine learning model may be used to determine changepoints within the second data and times associated with each changepoint. A second machine learning model may be used to determine a likelihood that the satellite pass will be successful based on at least one of the quantity of changepoints or the times associated with each changepoint, and a quality of service (QoS) score of a client may be updated based on the likelihood.